Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

eve-repo-upkeep前夕回购维护

Agent Skill

eve-repo-upkeep 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

5,866

周安装

235

GitHub Stars

公开资料未说明

下载量

1,899
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:eve-repo-upkeep(前夕回购维护)
来源仓库:https://github.com/incept5/eve-skillpacks
仓库路径:skills/eve-repo-upkeep
安装命令:
npx skills add https://github.com/incept5/eve-skillpacks --skill eve-repo-upkeep
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/incept5/eve-skillpacks --skill eve-repo-upkeep

简介

eve-repo-upkeep 用于维护应用仓库符合 Eve 平台规范,适合在 Codex、Claude、Cursor、Gemini CLI 中需要检查清单文件、验证配置或准备部署时使用。

  • 它可快速识别 .eve/manifest.yaml 和 skills.txt 等关键文件的完整性及状态,支持并行运行多个检查项以加快流程。
  • 使用时需结合具体任务场景判断是否需要深度扫描,建议在安装后通过原始 README 核验详细命令和输出格式。
  • 安装前应确认权限范围、仓库访问级别,以及是否涉及网络请求或配置文件修改等敏感操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Eve Repo Upkeep

Keep an app repo current with Eve conventions. The checks are independent — run them in parallel when multiple areas need attention.

When to Use

  • After Eve platform updates or manifest schema changes
  • Before a major deploy or release
  • When onboarding a new maintainer

Phase 1: Assess

Quickly determine which areas need attention. Check which of these files exist and whether they look stale — don't deep-read every file, just note which areas need work:

  • .eve/manifest.yaml — does it exist? Is the schema line eve/compose/v1?
  • skills.txt — does it exist? Are there pinned or obsolete entries?
  • AGENTS.md / CLAUDE.md — do they reference current skills?
  • agents/ directory — do agents.yaml, teams.yaml, chat.yaml exist?
  • Codebase — any obvious deprecated CLI patterns or inline secrets?

If only one area needs work, handle it directly. Otherwise, proceed to Phase 2.

Phase 2: Dispatch Workers

Create one worker per area that needs updating. Each worker description below is self-contained — a worker can execute its area independently without context from the others.

Worker: Manifest Alignment

Check and fix .eve/manifest.yaml:

  • Ensure schema: eve/compose/v1 is present.
  • Prefer services: over legacy components:.
  • Keep x-eve ingress and pipeline definitions accurate.
  • Keep x-eve.defaults in sync with harness defaults (harness/profile/options).
  • Keep x-eve.agents profiles aligned with orchestration policy.
  • Ensure x-eve.agents.config_path and x-eve.chat.config_path point to valid files.
  • Confirm ${secret.KEY} usage for secrets.
  • Deploy pipelines should include a build step before release.
  • Services with Docker images should have build.context defined.
  • Registry auth secrets (REGISTRY_USERNAME + REGISTRY_PASSWORD) are required only for custom BYO registries.

Worker: Skills File

Check and fix skills.txt:

  • Keep Eve skillpack references up to date.
  • Remove obsolete packs or pinned versions.

Worker: Agent Instructions

Check and fix AGENTS.md, CLAUDE.md, and agents/ config files:

  • Update skill references to include eve-se-index.
  • Remove stale commands or URLs.
  • agents/agents.yaml defines agents and skills — verify entries are current.
  • agents/teams.yaml defines team composition and dispatch — verify structure.
  • agents/chat.yaml defines chat routing rules and permissions — verify rules.

Worker: Deprecated Patterns

Search the codebase for deprecated patterns and fix or flag them:

  • Old CLI commands (eve deploy vs eve env deploy)
  • Old deploy syntax without --ref parameter
  • Hardcoded domains in docs or manifests
  • Inline secrets in repo files
  • Dockerfiles missing org.opencontainers.image.source label pointing to the repo URL
  • Pipelines missing build step before release
  • Services with Docker images but no build.context configuration
  • Missing registry authentication secrets for custom registries (REGISTRY_USERNAME, REGISTRY_PASSWORD or provider-equivalent names)

Phase 3: Verify

After all workers complete, run final verification:

# Local validation (Docker Compose)
docker compose up --build

# Staging deploy (requires --ref with 40-char SHA or a ref resolved against --repo-dir)
eve env deploy staging --ref main --repo-dir .

# Use --direct to bypass pipeline if needed
eve env deploy staging --ref main --repo-dir . --direct

Track the deploy job with eve job follow.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

39.22%
按下载量换算745

Claude

27.25%
按下载量换算517

Cursor

17.56%
按下载量换算333

Gemini CLI

9.68%
按下载量换算184

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills